© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 62592
    Prev
    Next
    INDEX
    Explanations

    knowledge and AI capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    owell
    -0.10
    coon
    -0.09
    seg
    -0.09
    loy
    -0.09
    रण
    -0.08
    tern
    -0.08
    âĢ²
    -0.08
    ctors
    -0.08
    ter
    -0.08
    rew
    -0.08
    POSITIVE LOGITS
    ed
    0.13
    ably
    0.11
    gable
    0.11
    fully
    0.10
    full
    0.10
    forman
    0.10
    ously
    0.10
    led
    0.09
    edly
    0.09
    here
    0.09
    Activations Density 0.012%

    No Known Activations